Abstract | ||
---|---|---|
Image-Based Rendering (IBR) allows high-fidelity free-viewpoint navigation using only a set of photographs and 3D reconstruction as input. It is often necessary or convenient to remove objects from the captured scenes, allowing a form of scene editing for IBR. This requires multi-view inpainting of the input images. Previous methods suffer from several major limitations: they lack true multi-view coherence, resulting in artifacts such as blur, they do not preserve perspective during inpainting, provide inaccurate depth completion and can only handle scenes with a few tens of images. Our approach addresses these limitations by introducing a new multi-view method that performs inpainting in intermediate, locally common planes. Use of these planes results in correct perspective and multi-view coherence of inpainting results. For efficient treatment of large scenes, we present a fast planar region extraction method operating on small image clusters. We adapt the resolution of inpainting to that required in each input image of the multi-view dataset, and carefully handle image resampling between the input images and rectified planes. We show results on large indoors and outdoors environments.
|
Year | DOI | Venue |
---|---|---|
2018 | 10.1145/3190834.3190846 | I3D |
Keywords | Field | DocType |
Inpainting,Multi-View,Image-Based Rendering | Computer vision,Computer graphics (images),Computer science,Inpainting,Coherence (physics),Planar,Artificial intelligence,Rendering (computer graphics),Image-based modeling and rendering,Image scaling,3D reconstruction | Conference |
ISBN | Citations | PageRank |
978-1-4503-5705-0 | 6 | 0.44 |
References | Authors | |
26 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Julien Philip | 1 | 31 | 1.58 |
George Drettakis | 2 | 2281 | 147.82 |